A natural scene text detection method based on full convolution neural network

Abstract

The invention discloses a natural scene text detection method based on full convolution neural network, This method uses CNN network to extract the feature representation of text, and adjusts the feature representation by feature fusion module, at the same time fuses the semantic feature of high-level feature map and the position information of low-level feature map, so that the extracted featurehas stronger representation ability, and combines with text prediction module to directly predict the candidate text object. This method adopts end-to-end training and prediction process, The processing flow is simple, and no multi-step hierarchical processing is needed. Finally, the final detection result is obtained by simple NMS operation, which has high accuracy and strong robustness. The multi-directional and multi-size text object in the natural scene image with complex background can be detected well, and the detection performance of the natural scene text is excellent.

Description

Technical field [0001] The invention belongs to the technical field of computer vision, and specifically relates to a natural scene text detection method based on a full convolutional neural network. Background technique [0002] Natural scene text usually carries rich semantic information about the scene and image content, and plays a very important role in many application fields such as image retrieval, annotation, and content analysis. Compared with the text in the scanned document, the appearance attributes such as font, size, direction and color of natural scene text and factors such as image background and lighting are more complex and changeable. At the same time, blur and resolution may occur when natural scene image is collected. Too low conditions make natural scene text detection a challenging task. [0003] Traditional natural scene text detection methods can be divided into two categories, namely text detection methods based on connected components and text detection...

AI Technical Summary

Problems solved by technology

These models generally contain multiple convolutional layers and pooling layers. The extraction of features at different levels is achieved through continuous convolution and pooling operations. On the one hand, the ability to express feature semantics is improved, but on the other hand, precise location information is also lost. , which affects the accurate detection of text objects to a certain extent

Images